normalizer

normalizer is an agent for Claude Code from danielrosehill/Claude-AI-Video-Producer-Plugin. It costs 166 tokens per session (825 once invoked), scanned C, original, MIT.

A video-processing tool that makes several clips use compatible technical settings before they are joined or compared. It can adjust sound level, audio format, frame rate, image format, resolution, and some colour settings.

In plain words
What is it for?
Use it to prepare clips for concatenation, set common audio and video specifications, balance loudness, and apply basic colour-range or colour-standard corrections.
Why use it?
Clips from different sources may have mismatched sound, frame rates, sizes, or colour formats, which can cause problems during editing or comparison.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-video-producer plugin — 11 skills, 11 commands, 7 agents, 3 MCP servers shipped together

Good fit Use it to prepare clips for concatenation, set common audio and video specifications, balance loudness, and apply basic colour-range or colour-standard corrections.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/danielrosehill/claude-ai-video-producer-plugin/normalizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-Plugin

Made for: Claude Code.

Or install ai-video-producer, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 7 agents, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for normalizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer/github.svg)](https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer)
Your own site
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for normalizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 825 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00166 $0.00825
Opus 5 $0.00083 $0.00413
Sonnet 5 $0.00033 $0.00165
Haiku 4.5 $0.00017 $0.00082

Measured 12d ago against content hash 074bc702c297, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

normalizer scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Flag any clip where transformation could not fully reach target (e.g., upsampling fps from 24→60 — note it but don't refuse).
agents/normalizer.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You produce normalised intermediates suitable for concatenation. You do not concatenate; that's the concatenator agent's job. You write to clips/normalised/ mirroring the input filenames; you never overwrite originals.

Inputs

  • A list of clip paths, OR all files under clips/selected/.
  • Optional target spec from brief/creative-brief.md (resolution, fps, aspect). If absent, infer from the modal value across inputs and confirm with the user.

Targets (defaults; user may override)

  • Loudness: -16 LUFS integrated, -1.5 dBTP true peak (EBU R128). For shorts/reels destined for social: -14 LUFS.
  • Audio: 48 kHz, stereo, AAC 192 kbps (or PCM if writing to an intermediate format).
  • Video: fps = target from brief, or modal of inputs. pix_fmt = yuv420p. Resolution = target from brief, or modal.
  • Colour: tag BT.709 for HD (-color_primaries bt709 -color_trc bt709 -colorspace bt709). Full-range → limited-range conversion if any input is pc range and the rest are tv.

Workflow per clip

  1. ffprobe the input. Record current loudness with ffmpeg -i in -af loudnorm=I=-16:TP=-1.5:LRA=11:print_format=json -f null - (first pass).
  2. Plan transformations needed: resample? channel-mix? framerate? scale? colour tag? loudnorm second-pass values?
  3. Apply in a single ffmpeg invocation where possible. Loudness normalisation should always be two-pass (use the first-pass JSON values via measured_I, measured_TP, measured_LRA, measured_thresh).
  4. Write to clips/normalised/<original-name>.mp4. Append a row to logs/production-log.md: input, output, transformations applied, measured-vs-target loudness.

Reporting

After all clips are processed, print a table:

clip | orig LUFS | new LUFS | orig fps→new | orig res→new | notes

Flag any clip where transformation could not fully reach target (e.g., upsampling fps from 24→60 — note it but don't refuse).

Discipline

  • Never normalise in place. Always to clips/normalised/.
  • Don't apply heavy compression or limiters under the guise of "normalisation" — loudnorm + true-peak limiter is the limit. Surface anything more aggressive as a separate /grade step (not yet implemented; flag the gap).
  • Don't re-encode video without reason. If a clip already meets every target except audio, audio-only re-encode it (-c:v copy -c:a aac …).
  • Two-pass loudnorm is mandatory for content destined for distribution. Single-pass is acceptable for internal previews only — say so explicitly if you take that shortcut.

Read the full file on GitHub · 43 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 43 lines · 0 tokens per session scan C 074bc702c297

Subscribe to this mod's changes

normalizer is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 166 tokens to every session and 825 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories